How to search on Oriane

oriane.xyz/how-to-search

Claude Download Claude Skill

Oriane indexes Instagram and TikTok at the frame level. Its AI analyzes what is on screen, what is spoken in audio, captions, hashtags, mentions, and context — all at once. This page explains how to use the search interface, what each filter does, how to combine them effectively, and what to do with the results.

A general principle before anything else: always search a bit wider than you think you need to. Oriane returns raw results. Noise is expected and manageable. Once you export the CSV, an AI like Claude will read every caption and transcript and re-filter to keep only what is relevant. A search that is too narrow costs you signal. A search that is too wide costs you nothing — the LLM sorts it out.

1. Filters

What filters are available

The Oriane search bar offers 12 filters that can be combined freely in a single search:

What each filter does

AI Vision

Describe what you want to see visually on screen. The input accepts natural language. Examples: "woman applying serum", "champagne being poured at a party", "blond girl brushing her hair".

A similarity threshold slider (default 70%) controls how strict the visual match is. Lower it to cast a wider net. Raise it to get closer visual matches only. If results seem off, check that results are sorted by "most similar visually" — the sort order matters here.

You can also upload a reference image instead of typing. Oriane will find videos that contain the same or visually similar moment. Useful for finding copies, derivatives, or content built around a campaign visual.

Important: AI Vision works well for universally recognized brands and highly distinctive visuals. Searching "Louis Vuitton bag" or "Mercedes car" or "Adidas shoes" will work because the model knows these brands visually. But "Tom Ford product" will not — the model has no reliable visual reference for that brand and will return videos of random people. Same applies to people: "Donald Trump" works, but even "Brad Pitt" may not. For niche brands or less globally prominent people, use Spoken Words or Caption instead — they are far more reliable for name-based searches.

Also: because AI Vision searches rely on visual frame analysis, they can produce false positives that a text-based filter would have caught. When AI Vision is part of your search, keep in mind that Claude currently cannot efficiently verify large volumes of images, so lean on the transcript and caption data in your CSV to filter out obvious visual mismatches during analysis.

Spoken Words

Filters by what is said aloud in the video audio — not what is written. This is one of the most powerful filters on the platform. Three modes:

When searching for a brand or name, always add spelling variants. "Jo Malone" may also appear in transcripts as "Joe Malone". Search for both. Similarly, go beyond the brand name itself — searching for "candle", "perfume", or "scent" alongside Jo Malone will surface relevant category content you would otherwise miss.

Language

Filter videos by the language spoken. Useful for market-specific research or multilingual brand tracking. The filter is any-based — one language per video. Oriane does not currently support multi-language detection within a single video.

Platforms

Filter by social platform: TikTok, Instagram, or both.

Date

Filter by time period. The current data window is the last 3 months. It is not possible to search beyond this range. Also note that Oriane needs up to one week to index new videos, so very recent content may not yet appear — this is normal.

Caption

Filters by the full written caption and description of the video. Uses the same three-mode logic as Spoken Words — and the same behavior: "contains approximately" searches for your words anywhere in the caption in any order, not as a phrase and not with synonym matching. "Contains exactly" finds the exact phrase. Caption is a broad signal: it includes everything written in the post, which means hashtags and mentions are also part of the caption text and will be caught by a Caption filter.

This makes Caption especially useful as a fallback. If you cannot find an account in the Mentions index, excluding it via Caption is a reliable alternative.

Mentions

Filter by accounts mentioned (@mentions) in the video post. Search an account name and Oriane suggests verified accounts with follower counts. Supports "any of these accounts are mentioned" and "any of these accounts are NOT mentioned". You can also paste a comma-separated list of accounts to add them in bulk.

Hashtags

Filter by hashtags used in the video post.

Published by

Filter to videos published by specific accounts. You must search by the exact username or handle of the account — not the display name or brand name. A company named "Deel" may have the handle "@letsdeel", and searching "Deel" will not find it. If you do not know the handle, look it up on the platform directly, find it from a previous Oriane search result (the Account Username column in any export), or ask an LLM to find it with a web search.

Also note: brands do not always use the same handle on Instagram and TikTok. Large corporations may also have multiple accounts split by language, region, or country — each with its own handle. You can paste a comma-separated list of handles to search multiple accounts in one go, and use the NOT published by exclusion to filter out brand-owned content and isolate third-party UGC.

Useful for: competitor content audits, adjacent niche creator research, brand safety checks on a creator's recent content (last 3 months) before signing a partnership. Because Oriane's data window is limited to the last 3 months, if you want more history on a creator you are considering working with, start monitoring them early — do not wait until the last minute to run a safety check or you will only see a fraction of their output.

Note: Oriane does not index videos from accounts with fewer than 5,000 followers. Searching for very small accounts will return no results.

Followers

Filter creator accounts by follower count. Set a min and max, or use quick presets: 10K, 100K, 500K, 1M. Minimum indexed account size is 5,000 followers.

Views

Filter videos by view count range. Min and max with quick presets. Use to focus on high-performing content, or to find hidden gems with strong engagement despite modest reach.

Engagement Rate

Filter by engagement percentage or total interactions (likes, comments, shares, saves). Toggle between percentage and interaction count depending on whether you want relative or absolute performance.

How to combine filters well — by use case

Finding brand mentions your tools missed

Use Spoken Words (contains exactly: your brand name) combined with Caption (doesn't contain: your brand name). This isolates videos where your brand is spoken aloud but never written in the caption — pure Shadow Reach. These are the videos every text-based listening tool misses entirely.

Researching a trend or content category

Start with AI Vision to describe the visual context, and add Spoken Words (approximately) to capture the verbal dimension of the topic. Set a date range to see momentum. Search wider than necessary — the LLM will re-filter. Keep in mind that very recent videos (within the past week) may not yet be indexed.

Finding creators for a partnership

Think beyond brand names. Use AI Vision with descriptive queries tied to the content context you care about — "blond girl brushing her hair" if you are launching a shampoo for blonds, for example. Combine with a Followers range to scope to your target tier and an Engagement Rate minimum to ensure active audiences. The results are creators who already produce relevant content organically.

Vetting a creator before signing

Use Published by to scope the search to the creator's account. Do not apply additional filters — retrieve their full indexed video history as-is. Export the CSV and give it to Claude with your specific red flag criteria: competitor mentions, language issues, off-brand content, engagement drop-off. You can batch up to 200 creators in a single Published by search and export all their videos in one CSV.

Competitor intelligence

Use Published by with your competitor's account to audit their content strategy: formats, topics, products, posting cadence, and what drives their highest engagement. Run a separate search using Mentions set to their account to find third-party creators already organically talking about them. Spoken Words (contains exactly: competitor name) is also highly effective — same logic as brand tracking.

Campaign measurement

Run the same core search before and after a campaign, scoped with the Date filter to isolate each period. Use Hashtags to isolate activated content, then exclude it in a second search to measure organic halo separately. Save searches to favorites and rename them — this makes refreshing campaign tracking much faster without rebuilding the search each time.

2. Exporting data

After any search, click the export button to download a CSV of the results. Select which columns to include before downloading. Up to 10,000 rows per search.

Available export columns:

The file is UTF-8 encoded. When parsing with Python or pandas, use encoding="utf-8-sig" to avoid BOM issues on the first column. Engagement Rate values are decimals — multiply by 100 to get the percentage.

3. Analyzing with AI

Once you have a CSV, drag it into Claude, ChatGPT, Gemini, or Copilot alongside a prompt. The AI reads every row — captions, transcripts, engagement data, creator details — and generates a structured intelligence report.

Oriane's prompt library covers the most common report types:

Each prompt includes full instructions for noise filtering, data cleaning, analysis framework, and HTML report design. Ready to copy and paste directly.

Prompt library: oriane.xyz/prompt-library

Browse example reports built from real Oriane data — Shadow Reach analyses, brand intelligence reports, and trend reports across categories — to see what the output looks like before running your own search.

Example reports: oriane.xyz/explore

4. Step-by-step guides by use case

For a walkthrough of the full process for each specific use case — from search setup to insight — see:

Oriane — AI Video Intelligence · oriane.xyz